{"data":{"slug":"jgravelle-jcodemunch-mcp","name":"jcodemunch-mcp","tagline":"Cut AI token costs 95%+ on code exploration through precise symbol-level GitHub code retrieval","github_url":"https://github.com/jgravelle/jcodemunch-mcp","owner":"jgravelle","repo":"jcodemunch-mcp","owner_avatar_url":"https://avatars.githubusercontent.com/u/3400540?v=4","primary_language":"Python","stars":2700,"forks":370,"topics":["ai-coding","ast","claude","claude-code","cline","code-intelligence","codex","context-window","copilot","cursor","developer-tools","gemini-cli","llm","mcp","mcp-server","model-context-protocol","opencode","token-optimization","tree-sitter","windsurf"],"archived":false,"github_pushed_at":"2026-09-20T03:29:10+00:00","maintenance_label":"Very active","stars_delta_30d":464,"url":"https://www.graphcanon.com/tools/jgravelle-jcodemunch-mcp","markdown_url":"https://www.graphcanon.com/tools/jgravelle-jcodemunch-mcp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jgravelle-jcodemunch-mcp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jgravelle-jcodemunch-mcp","description":"Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.","homepage_url":"https://jcodemunch.com/","license":"Other","open_issues":33,"watchers":21,"ai_summary":"A high-efficiency MCP (Model Context Protocol) server leveraging tree-sitter AST for accurate, token-optimized coding assistance and retrieval.","readme_excerpt":"## Install\n\n#### One-click installs\n\n\n\n\n\n#### Recommended: one command\n\n```bash\nuv tool install jcodemunch-mcp\njcodemunch-mcp init\n```\n\nNo virtualenv to manage, nothing written into system Python, and it works as-is on PEP 668 distros (Ubuntu 24.04+, Debian 12+) where bare `pip install` is refused. [Don't have `uv` yet?](https://docs.astral.sh/uv/getting-started/installation/)\n\n`init` auto-detects your MCP clients (Claude Code, Claude Desktop, Cursor, Windsurf, Continue), writes their config entries, installs the CLAUDE.md prompt policy so your agent actually uses jCodeMunch, optionally installs enforcement hooks, optionally indexes your project, and audits your agent config files for token waste.\n\n<details>\n<summary><b>Other install paths</b></summary>\n\n| Command | Use it when |\n|---|---|\n| `uvx jcodemunch-mcp` | **Zero install.** Runs from an ephemeral environment — nothing lands on disk permanently. The client entries `init` writes already invoke the server this way, so for most setups this is all that ever runs. ⚠ Enforcement hooks are the exception: they're spawned by a minimal-PATH subshell and resolve the executable by name, so they need `uv tool install` (or `pipx`/`pip`) to work. |\n| `pipx install jcodemunch-mcp` | You already standardise on pipx |\n| `pip install jcodemunch-mcp` | Inside a virtualenv you manage yourself |\n\n</details>\n\nVerify:\n\n```bash\njcodemunch-mcp --version\n```\n\n#### Manual Claude Code setup\n\n```bash\nclaude mcp add -s user jcodemunch -- uvx jcodemunch-mcp\n```\n\nNo install step — `uvx` fetches and runs the server on demand. Prefer it on your PATH (and required for enforcement hooks)? `uv tool install jcodemunch-mcp`, then `claude mcp add -s user jcodemunch jcodemunch-mcp`.\n\nThen tell the agent to prefer the tools. This matters more than people think; installation makes the tools available but does not break the agent's brute-reading habit. One line in your CLAUDE.md does it:\n\n```markdown\nCall the jcodemunch_guide tool and strictly follow its instructions.\n```\n\nUsing Cursor, Windsurf, Codex CLI, Antigravity, Gemini CLI, Qwen Code, Kiro, Cline, Zed, Goose, Hermes, Odysseus, or Paperclip? Every tested client configuration lives in **[CLIENTS.md](CLIENTS.md)**. Optional extras (local semantic search, AI summaries per provider) are in [QUICKSTART.md](QUICKSTART.md); the system surfaces each extra pulls in are documented in [SECURITY.md](SECURITY.md#optional-extras--system-surfaces-each-pulls-in).\n\n---\n\n---\n\n## Licensing and commercial use\n\njCodeMunch-MCP is released under the **jCodeMunch-MCP Dual-Use License** ([full terms](LICENSE)). **Free for non-commercial use. Commercial use requires a paid license**, one-time, sold by jMunch LLC via Stripe:\n\n**jCodeMunch-only:** [Builder, $79](https://jcodemunch.com/descriptions.php#builder) (1 developer) · [Studio, $349](https://jcodemunch.com/descriptions.php#studio) (up to 5) · [Platform, $1,999](https://jcodemunch.com/descriptions.php#platform) (org-wide internal deployment)\n\n**Full jMunch suite (code + docs + data):** [Trio Builder, $99](https://jcodemunch.com/descriptions.php#builder) · [Trio Studio, $449](https://jcodemunch.com/descriptions.php#studio) · [Trio Platform, $2,499](https://jcodemunch.com/descriptions.php#platform)\n\nNot sure it's worth it? Run your own numbers through the [ROI calculator](https://jcodemunch.com/roi.php?utm_source=github&utm_medium=readme&utm_campaign=jcm_readme_bottom), or forward [the finance-team version](https://jcodemunch.com/for-finance.php?utm_source=github&utm_medium=readme&utm_campaign=jcm_readme_bottom) to whoever signs off. The guarantee stands: if jCodeMunch doesn't pay for itself, you don't pay for jCodeMunch.\n\nConditions on all uses: retain the copyright notice, clearly mark modifications and keep the original author's name intact (he's kinda full of himself), and include a prominent modification notice in source redistributions. The Software may not be renamed, rebranded, or published to any public package registry,","github_created_at":"2026-02-09T01:58:27+00:00","created_at":"2026-07-11T11:51:23.365825+00:00","updated_at":"2026-09-20T06:41:12.069405+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai-coding","name":"ai-coding"},{"slug":"ai-tools","name":"ai-tools"},{"slug":"ast","name":"ast"},{"slug":"claude-code","name":"claude-code"},{"slug":"code-intelligence","name":"code-intelligence"},{"slug":"github","name":"github"},{"slug":"mcp-server","name":"mcp-server"}],"trust":{"provenance":{"is_fork":false,"github_id":1153178500,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T03:53:30.913Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-16T14:04:32Z","stars_delta_30d":464,"open_issues_delta_30d":26},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-12T04:02:39.359Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T03:53:31.889Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T03:53:31.889Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T03:53:31.889Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T03:53:31.889Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T03:53:31.889Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T03:53:31.889Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T03:53:31.889Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- Use jcodemunch-mcp when you are working on projects where minimizing AI token usage is crucial, as it can save up to 95% of tokens.","- Utilize this tool if you need precise symbol-level code retrieval from GitHub within your application development process."],"when_not_to_use":["- Avoid jcodemunch-mcp if your primary focus does not involve token optimization and you are willing to use more general MCP services without strong token-economy incentives.","- Do not opt for this tool if working with codebases or systems that do not rely heavily on GitHub repositories, as its retrieval feature is optimized for GitHub."],"source":"enrich:decision_facts","observed_at":"2026-07-12T05:05:15.410Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"jcodemunch-mcp is a high-efficiency MCP server that uses tree-sitter AST for precise, symbol-level GitHub code retrieval. It aims to provide coding assistance and retrieval with significant token cost savings."}]}}